HSEMath

Задача 3 (2 балла)
def any_news_about_harry(url):
    import urllib.request
    try:
        f = urllib.request.urlopen(url)
        if "Harry" in str(f.read()):
            return True
        else:
            return False
    except:
        False
Задача 2 (1 балл)
def get_strong(html):
    import bs4
    soup = bs4.BeautifulSoup(html, "html.parser")
    return soup.strong.text
Задача 3 (1 балл)
def all_images_src(xml):
            import bs4
            soup = bs4.BeautifulSoup(xml, "html.parser")
            res = []
            for a in soup.find_all(['img']):
                res.append(a['src'])
            return res
Задача 4 (2 балла)
from urllib.parse import urlencode
entrypoint = "https://ru.wikipedia.org/w/index.php?"
def mkurl(title, oldid):
    return entrypoint+urlencode(dict(title=title, oldid=oldid))

def get_all_headings(url):
    import bs4
    import urllib.request
    res = []
    try:
        f = urllib.request.urlopen(url)
        soup = bs4.BeautifulSoup(f.read(), "html.parser")
        s = None
        for a in soup.find_all(['span'], {'class': 'mw-headline'}):
             if 'h2'in str(a.parent):
                 res.append(a.parent.find(['span'], {'class': 'mw-headline'}).text)
        return res
    except:
        return ["Not found"]

Задача 5 (3 балла)
from urllib.parse import urlencode
entrypoint = "https://ru.wikipedia.org/w/index.php?"
def mkurl(title):
    return entrypoint+urlencode(dict(title=title))

def city_site(name):
    url = mkurl(name)
    import bs4
    import urllib.request

    try:
        f = urllib.request.urlopen(url)
        soup = bs4.BeautifulSoup(f.read(), "html.parser")

        for a in soup.find_all(['tr']):
            buferVar = a.find('th')
            if buferVar != None and buferVar.text == "Официальный сайт":
                return a.find(['a'], {'class': 'external text'})['href']

    except:
        return None




Задача 6 (4 балла)

def get_languages_hse(last_name):
    def get_teacher_url(last_name):
        url = 'https://www.hse.ru/org/hse/ouk/hmat/persons'
        import bs4
        import urllib.request

        try:
            f = urllib.request.urlopen(url)
            soup = bs4.BeautifulSoup(f.read(), "html.parser")
            s = None
            for a in soup.find_all(['a'], {'class': 'fa-person__name'}):
                if last_name in a.text:
                    return 'http://' + a['href'][2:]
        except:
            return None
    # coding=utf8
    url = get_teacher_url(last_name)

    import bs4
    import urllib.request
    res = []

    try:
        f = urllib.request.urlopen(url)
        soup = bs4.BeautifulSoup(f.read(), "html.parser")
        for a in soup.find_all(['dl'],{'class':'main-list large main-list-language-knowledge-level'}):
            for r in a.find_all('dd'):
                res.append(r.text)
            return res
    except:
        pass